← Back to Skills Marketplace
Watermark Remover
by
TechhnicistSmallWhite
· GitHub ↗
· v1.0.0
526
Downloads
0
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install watermark-remover
Description
去除 PDF 文件中的水印。使用场景：用户请求去除 PDF 文件的水印时触发。支持单个或多个文件批量处理。严格遵循确认流程：环境检查→库安装确认→水印检测→去除确认。
README (SKILL.md)
Watermark Remover - PDF 水印去除技能
工作流程
1. 触发条件
当用户请求去除文件水印时触发，例如：
- "帮我去除这个 PDF 的水印"
- "把这个文件的水印去掉"
- "去除这些文件的水印"
2. 环境检查流程
第一步：检查 Python 环境
python --version
- 如果 Python 未安装 → 必须获得用户确认后才能安装
- 如果已安装 → 继续下一步
第二步：检查所需 Python 库
需要检查以下库：
pypdf- PDF 处理PyMuPDF(fitz) - PDF 分析和验证
检查命令：
python scripts/check_env.py check_all
- 如果库未安装 → 必须获得用户确认后才能安装
- 如果已安装 → 继续下一步
3. 水印检测
使用 Python 脚本检测文件中的水印：
python scripts/detect_watermark.py \x3C文件路径>
检测内容包括：
- 水印类型（Pattern/图像/文本）
- 水印位置
- 保存水印预览图到指定位置
必须向用户展示检测结果并确认是否开始去除水印。
4. 去除水印
获得用户确认后执行：
python scripts/remove_watermark.py \x3C文件路径> [--output \x3C输出路径>]
输出规则：
- 如果用户指定输出路径 → 保存到指定位置
- 如果用户未指定 → 保存到原文件同级目录
- 命名格式：
\x3C原文件名>_no_watermark.\x3C扩展名>
5. 验证结果
去除完成后自动验证：
- 检查输出文件是否存在
- 检查水印是否已移除
- 向用户展示验证结果
脚本说明
scripts/check_env.py
检查 Python 环境和所需库的安装状态。
scripts/detect_watermark.py
检测 PDF 文件中的水印，生成预览图。
scripts/remove_watermark.py
执行水印去除操作。
安全确认原则
⚠️ 以下操作必须获得用户明确确认后才能执行：
- 安装 Python
- 安装 Python 库（pip install）
- 删除或修改任何文件
- 修改系统配置文件
- 开始执行水印去除操作
示例对话
用户: 帮我去除这个 PDF 的水印
助手:
- 检测到您需要去除水印，让我先检查环境...
- ✓ Python 已安装 (3.x.x)
- ⚠ 缺少库 pypdf，需要安装吗？(y/n)
- [用户确认后安装]
- ✓ 环境准备完成
- 检测到水印：CodeCV 简历（Pattern 类型）
- 预览图已保存：xxx_watermark_preview.png
- 确认开始去除水印吗？(y/n)
- [用户确认后执行]
- ✓ 水印已去除，文件保存至：xxx_no_watermark.pdf
Usage Guidance
This package appears to do what it says and does not request secrets or network access, but the source/homepage is unknown. Before installing or running: (1) review the included scripts yourself or in a sandboxed environment, (2) back up original PDFs (the tool writes new files and could overwrite if names collide), (3) confirm the tool prompts and you explicitly allow any pip installs, (4) be aware of legal/ethical concerns — removing watermarks may violate copyright or terms of service. If you want higher assurance, run the scripts in an isolated VM or container and inspect the code line-by-line (the code here is small and readable).
Capability Analysis
Type: OpenClaw Skill
Name: watermark-remover
Version: 1.0.0
The skill bundle is a legitimate tool for removing watermarks from PDF files using the pypdf and PyMuPDF libraries. The instructions in SKILL.md emphasize safety by requiring explicit user confirmation for environment changes (pip installs) and file modifications. While scripts/remove_watermark.py contains a minor Python coding error (variable shadowing in the main function that would cause a crash during verification), there is no evidence of malicious intent, data exfiltration, or unauthorized access.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md and included scripts (check_env.py, detect_watermark.py, remove_watermark.py) align: all scripts operate on the provided PDF path and implement detection and removal logic. No unrelated binaries, cloud credentials, or config paths are requested.
Instruction Scope
SKILL.md limits actions to local environment checks, optional pip installs (with explicit user confirmation), watermark detection, user confirmation, removal, and verification. Scripts only read/write files referenced by the user and output previews/results. The instructions explicitly require user consent before installations or modifying files.
Install Mechanism
No install spec is present (instruction-only skill). The scripts may call pip (via provided install commands shown by check_env.py) if the user consents; there are no downloads from remote URLs or archive extraction steps in the skill metadata.
Credentials
The skill requires no environment variables, credentials, or config paths. The only environment information surfaced by the scripts is Python executable/version and library presence (used to decide whether to prompt for installs), which is proportional to the task.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills/configurations. It writes output files to the same directory (or as specified) which is expected behavior for file-processing tools.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install watermark-remover - After installation, invoke the skill by name or use
/watermark-remover - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the watermark-remover skill for removing watermarks from PDF files.
- Supports batch processing of single or multiple PDFs.
- Implements a strict step-by-step confirmation workflow: environment check → library installation confirmation → watermark detection → user confirmation before removal.
- Automatically generates watermark preview images and displays results for user validation.
- Ensures all environment changes and file modifications occur only after explicit user approval.
Metadata
Frequently Asked Questions
What is Watermark Remover?
去除 PDF 文件中的水印。使用场景：用户请求去除 PDF 文件的水印时触发。支持单个或多个文件批量处理。严格遵循确认流程：环境检查→库安装确认→水印检测→去除确认。 It is an AI Agent Skill for Claude Code / OpenClaw, with 526 downloads so far.
How do I install Watermark Remover?
Run "/install watermark-remover" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Watermark Remover free?
Yes, Watermark Remover is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Watermark Remover support?
Watermark Remover is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Watermark Remover?
It is built and maintained by TechhnicistSmallWhite (@techhnicistsmallwhite); the current version is v1.0.0.
More Skills